A treasure chest for visual classification and recognition powered by PaddlePaddle

Official Pytorch implementation of CutMix regularizer

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)

An open-source toolkit which is full of handy functions, including the most used models and utilities for deep-learning practitioners!

Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.

Keras implementation of CutMix regularizer

Official PyTorch implementation of DiffuseMix : Label-Preserving Data Augmentation with Diffusion Models (CVPR'2024)

FastClassification is a tensorflow toolbox for class classification. It provides a training module with various backbones and training tricks towards state-of-the-art class classification.

Official Codes and Pretrained Models for RecursiveMix

Deep learning solution for Cassava Leaf Disease Classification, a Kaggle's Research Code Competition using Tensorflow.

tensorflow2 implementation of SnapMix as described in SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Implementation of an advanced Convolutional Neural Network (CNN) for large-scale pest recognition, incorporating augmentation techniques and regularizers for improved accuracy and generalization.

This is a TensorFlow implementation of the following paper: DropBlock: A regularization method for convolutional networks

Tensorflow2(Keras)のImageDataGeneratorのJupyter上での実行例。

Image Classification Using Swin Transformer With RandAugment, CutMix, and MixUp

PyTorch implementation of 'ViT' (Dosovitskiy et al., 2020) and training it on CIFAR-10 and CIFAR-100

Implementation of CutMix Augmentation with Keras.

CutMix Implementation in PyTorch

Tensorflow2/KerasのImageDataGenerator向けのcutmixの実装。